© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173218
    Prev
    Next
    INDEX
    Explanations

    coverage of events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     μη
    0.22
     Photonics
    0.22
     зро
    0.21
     Green
    0.20
     curricula
    0.20
     дослід
    0.20
     Carrington
    0.20
    橡
    0.20
     differential
    0.20
     dissatisfaction
    0.20
    POSITIVE LOGITS
     Balliye
    0.26
    itatea
    0.25
    activate
    0.23
    itty
    0.22
     organise
    0.22
    cage
    0.22
    broadcast
    0.21
     hrvats
    0.21
     venezolano
    0.21
    izado
    0.20
    Activations Density 0.000%

    No Known Activations